Update Unicode data to 11.0.0. Change-Id: I924624f99e1cdea2485be893e657f0ca6a9aa08a Reviewed-on: https://code-review.googlesource.com/29230 Reviewed-by: Paul Wankadia <junyer@google.com>
diff --git a/doc/syntax.txt b/doc/syntax.txt index 92e2f2a..c87494e 100644 --- a/doc/syntax.txt +++ b/doc/syntax.txt
@@ -260,6 +260,7 @@ Cyrillic Deseret Devanagari +Dogra Duployan Egyptian_Hieroglyphs Elbasan @@ -270,9 +271,11 @@ Grantha Greek Gujarati +Gunjala_Gondi Gurmukhi Han Hangul +Hanifi_Rohingya Hanunoo Hatran Hebrew @@ -300,11 +303,13 @@ Lycian Lydian Mahajani +Makasar Malayalam Mandaic Manichaean Marchen Masaram_Gondi +Medefaidrin Meetei_Mayek Mende_Kikakui Meroitic_Cursive @@ -327,6 +332,7 @@ Old_North_Arabian Old_Permic Old_Persian +Old_Sogdian Old_South_Arabian Old_Turkic Oriya @@ -347,6 +353,7 @@ Siddham SignWriting Sinhala +Sogdian Sora_Sompeng Soyombo Sundanese
diff --git a/re2/unicode.py b/re2/unicode.py index 2899c87..deff4d8 100644 --- a/re2/unicode.py +++ b/re2/unicode.py
@@ -9,7 +9,7 @@ import urllib2 # Directory or URL where Unicode tables reside. -_UNICODE_DIR = "http://www.unicode.org/Public/10.0.0/ucd" +_UNICODE_DIR = "https://www.unicode.org/Public/11.0.0/ucd" # Largest valid Unicode code value. _RUNE_MAX = 0x10FFFF @@ -148,7 +148,7 @@ raise InputError("invalid number of fields %d" % (nfields,)) if type(filename) == str: - if filename.startswith("http://"): + if filename.startswith("https://"): fil = urllib2.urlopen(filename) else: fil = open(filename, "r")
diff --git a/re2/unicode_casefold.cc b/re2/unicode_casefold.cc index 1686943..b4da09d 100644 --- a/re2/unicode_casefold.cc +++ b/re2/unicode_casefold.cc
@@ -7,7 +7,7 @@ namespace re2 { -// 1295 groups, 2620 pairs, 343 ranges +// 1374 groups, 2778 pairs, 349 ranges const CaseFold unicode_casefold[] = { { 65, 90, 32 }, { 97, 106, -32 }, @@ -210,6 +210,8 @@ { 4256, 4293, 7264 }, { 4295, 4295, 7264 }, { 4301, 4301, 7264 }, + { 4304, 4346, 3008 }, + { 4349, 4351, 3008 }, { 5024, 5103, 38864 }, { 5104, 5109, 8 }, { 5112, 5117, -8 }, @@ -222,6 +224,8 @@ { 7302, 7302, -6236 }, { 7303, 7303, -6181 }, { 7304, 7304, 35266 }, + { 7312, 7354, -3008 }, + { 7357, 7359, -3008 }, { 7545, 7545, 35332 }, { 7549, 7549, 3814 }, { 7680, 7776, EvenOdd }, @@ -337,7 +341,7 @@ { 42929, 42929, -42282 }, { 42930, 42930, -42261 }, { 42931, 42931, 928 }, - { 42932, 42935, EvenOdd }, + { 42932, 42937, EvenOdd }, { 43859, 43859, -928 }, { 43888, 43967, -38864 }, { 65313, 65338, 32 }, @@ -350,12 +354,14 @@ { 68800, 68850, -64 }, { 71840, 71871, 32 }, { 71872, 71903, -32 }, + { 93760, 93791, 32 }, + { 93792, 93823, -32 }, { 125184, 125217, 34 }, { 125218, 125251, -34 }, }; -const int num_unicode_casefold = 343; +const int num_unicode_casefold = 349; -// 1295 groups, 1325 pairs, 191 ranges +// 1374 groups, 1404 pairs, 194 ranges const CaseFold unicode_tolower[] = { { 65, 90, 32 }, { 181, 181, 775 }, @@ -466,6 +472,8 @@ { 7302, 7302, -6204 }, { 7303, 7303, -6180 }, { 7304, 7304, 35267 }, + { 7312, 7354, -3008 }, + { 7357, 7359, -3008 }, { 7680, 7828, EvenOddSkip }, { 7835, 7835, -58 }, { 7838, 7838, -7615 }, @@ -540,16 +548,17 @@ { 42929, 42929, -42282 }, { 42930, 42930, -42261 }, { 42931, 42931, 928 }, - { 42932, 42934, EvenOddSkip }, + { 42932, 42936, EvenOddSkip }, { 43888, 43967, -38864 }, { 65313, 65338, 32 }, { 66560, 66599, 40 }, { 66736, 66771, 40 }, { 68736, 68786, 64 }, { 71840, 71871, 32 }, + { 93760, 93791, 32 }, { 125184, 125217, 34 }, }; -const int num_unicode_tolower = 191; +const int num_unicode_tolower = 194;
diff --git a/re2/unicode_groups.cc b/re2/unicode_groups.cc index ba104d2..8052827 100644 --- a/re2/unicode_groups.cc +++ b/re2/unicode_groups.cc
@@ -145,7 +145,7 @@ { 68028, 68029 }, { 68032, 68047 }, { 68050, 68095 }, - { 68160, 68167 }, + { 68160, 68168 }, { 68221, 68222 }, { 68253, 68255 }, { 68331, 68335 }, @@ -154,14 +154,21 @@ { 68521, 68527 }, { 68858, 68863 }, { 69216, 69246 }, + { 69405, 69414 }, + { 69457, 69460 }, { 69714, 69733 }, { 70113, 70132 }, { 71482, 71483 }, { 71914, 71922 }, { 72794, 72812 }, { 93019, 93025 }, - { 119648, 119665 }, + { 93824, 93846 }, + { 119520, 119539 }, + { 119648, 119672 }, { 125127, 125135 }, + { 126065, 126123 }, + { 126125, 126127 }, + { 126129, 126132 }, { 127232, 127244 }, }; static const URange16 Lo_range16[] = { @@ -171,7 +178,7 @@ { 448, 451 }, { 660, 660 }, { 1488, 1514 }, - { 1520, 1522 }, + { 1519, 1522 }, { 1568, 1599 }, { 1601, 1610 }, { 1646, 1647 }, @@ -310,8 +317,7 @@ { 4206, 4208 }, { 4213, 4225 }, { 4238, 4238 }, - { 4304, 4346 }, - { 4349, 4680 }, + { 4352, 4680 }, { 4682, 4685 }, { 4688, 4694 }, { 4696, 4696 }, @@ -342,7 +348,7 @@ { 6016, 6067 }, { 6108, 6108 }, { 6176, 6210 }, - { 6212, 6263 }, + { 6212, 6264 }, { 6272, 6276 }, { 6279, 6312 }, { 6314, 6314 }, @@ -382,12 +388,12 @@ { 12447, 12447 }, { 12449, 12538 }, { 12543, 12543 }, - { 12549, 12590 }, + { 12549, 12591 }, { 12593, 12686 }, { 12704, 12730 }, { 12784, 12799 }, { 13312, 19893 }, - { 19968, 40938 }, + { 19968, 40943 }, { 40960, 40980 }, { 40982, 42124 }, { 42192, 42231 }, @@ -406,7 +412,7 @@ { 43138, 43187 }, { 43250, 43255 }, { 43259, 43259 }, - { 43261, 43261 }, + { 43261, 43262 }, { 43274, 43301 }, { 43312, 43334 }, { 43360, 43388 }, @@ -502,7 +508,7 @@ { 68096, 68096 }, { 68112, 68115 }, { 68117, 68119 }, - { 68121, 68147 }, + { 68121, 68149 }, { 68192, 68220 }, { 68224, 68252 }, { 68288, 68295 }, @@ -512,10 +518,15 @@ { 68448, 68466 }, { 68480, 68497 }, { 68608, 68680 }, + { 68864, 68899 }, + { 69376, 69404 }, + { 69415, 69415 }, + { 69424, 69445 }, { 69635, 69687 }, { 69763, 69807 }, { 69840, 69864 }, { 69891, 69926 }, + { 69956, 69956 }, { 69968, 70002 }, { 70006, 70006 }, { 70019, 70066 }, @@ -549,7 +560,8 @@ { 71168, 71215 }, { 71236, 71236 }, { 71296, 71338 }, - { 71424, 71449 }, + { 71424, 71450 }, + { 71680, 71723 }, { 71935, 71935 }, { 72192, 72192 }, { 72203, 72242 }, @@ -557,6 +569,7 @@ { 72272, 72272 }, { 72284, 72323 }, { 72326, 72329 }, + { 72349, 72349 }, { 72384, 72440 }, { 72704, 72712 }, { 72714, 72750 }, @@ -566,6 +579,11 @@ { 72968, 72969 }, { 72971, 73008 }, { 73030, 73030 }, + { 73056, 73061 }, + { 73063, 73064 }, + { 73066, 73097 }, + { 73112, 73112 }, + { 73440, 73458 }, { 73728, 74649 }, { 74880, 75075 }, { 77824, 78894 }, @@ -578,7 +596,7 @@ { 93053, 93071 }, { 93952, 94020 }, { 94032, 94032 }, - { 94208, 100332 }, + { 94208, 100337 }, { 100352, 101106 }, { 110592, 110878 }, { 110960, 111355 }, @@ -897,7 +915,9 @@ { 1323, 1323 }, { 1325, 1325 }, { 1327, 1327 }, - { 1377, 1415 }, + { 1376, 1416 }, + { 4304, 4346 }, + { 4349, 4351 }, { 5112, 5117 }, { 7296, 7304 }, { 7424, 7467 }, @@ -1219,8 +1239,10 @@ { 42917, 42917 }, { 42919, 42919 }, { 42921, 42921 }, + { 42927, 42927 }, { 42933, 42933 }, { 42935, 42935 }, + { 42937, 42937 }, { 43002, 43002 }, { 43824, 43866 }, { 43872, 43877 }, @@ -1234,6 +1256,7 @@ { 66776, 66811 }, { 68800, 68850 }, { 71872, 71903 }, + { 93792, 93823 }, { 119834, 119859 }, { 119886, 119892 }, { 119894, 119911 }, @@ -1366,6 +1389,7 @@ }; static const URange32 Nd_range32[] = { { 66720, 66729 }, + { 68912, 68921 }, { 69734, 69743 }, { 69872, 69881 }, { 69942, 69951 }, @@ -1379,6 +1403,7 @@ { 71904, 71913 }, { 72784, 72793 }, { 73040, 73049 }, + { 73120, 73129 }, { 92768, 92777 }, { 93008, 93017 }, { 120782, 120831 }, @@ -1681,6 +1706,8 @@ { 4295, 4295 }, { 4301, 4301 }, { 5024, 5109 }, + { 7312, 7354 }, + { 7357, 7359 }, { 7680, 7680 }, { 7682, 7682 }, { 7684, 7684 }, @@ -1995,6 +2022,7 @@ { 42922, 42926 }, { 42928, 42932 }, { 42934, 42934 }, + { 42936, 42936 }, { 65313, 65338 }, }; static const URange32 Lu_range32[] = { @@ -2002,6 +2030,7 @@ { 66736, 66771 }, { 68736, 68786 }, { 71840, 71871 }, + { 93760, 93791 }, { 119808, 119833 }, { 119860, 119885 }, { 119912, 119937 }, @@ -2187,7 +2216,9 @@ { 2404, 2405 }, { 2416, 2416 }, { 2557, 2557 }, + { 2678, 2678 }, { 2800, 2800 }, + { 3204, 3204 }, { 3572, 3572 }, { 3663, 3663 }, { 3674, 3675 }, @@ -2238,7 +2269,7 @@ { 11824, 11833 }, { 11836, 11839 }, { 11841, 11841 }, - { 11843, 11849 }, + { 11843, 11854 }, { 12289, 12291 }, { 12349, 12349 }, { 12539, 12539 }, @@ -2293,12 +2324,13 @@ { 68336, 68342 }, { 68409, 68415 }, { 68505, 68508 }, + { 69461, 69465 }, { 69703, 69709 }, { 69819, 69820 }, { 69822, 69825 }, { 69952, 69955 }, { 70004, 70005 }, - { 70085, 70089 }, + { 70085, 70088 }, { 70093, 70093 }, { 70107, 70107 }, { 70109, 70111 }, @@ -2312,16 +2344,19 @@ { 71233, 71235 }, { 71264, 71276 }, { 71484, 71486 }, + { 71739, 71739 }, { 72255, 72262 }, { 72346, 72348 }, { 72350, 72354 }, { 72769, 72773 }, { 72816, 72817 }, + { 73463, 73464 }, { 74864, 74868 }, { 92782, 92783 }, { 92917, 92917 }, { 92983, 92987 }, { 92996, 92996 }, + { 93847, 93850 }, { 113823, 113823 }, { 121479, 121483 }, { 125278, 125279 }, @@ -2353,6 +2388,7 @@ }; static const URange32 C_range32[] = { { 69821, 69821 }, + { 69837, 69837 }, { 113824, 113827 }, { 119155, 119162 }, { 917505, 917505 }, @@ -2479,6 +2515,7 @@ { 69808, 69810 }, { 69815, 69816 }, { 69932, 69932 }, + { 69957, 69958 }, { 70018, 70018 }, { 70067, 70069 }, { 70079, 70080 }, @@ -2511,7 +2548,8 @@ { 71350, 71350 }, { 71456, 71457 }, { 71462, 71462 }, - { 72199, 72200 }, + { 71724, 71726 }, + { 71736, 71736 }, { 72249, 72249 }, { 72279, 72280 }, { 72343, 72343 }, @@ -2520,6 +2558,10 @@ { 72873, 72873 }, { 72881, 72881 }, { 72884, 72884 }, + { 73098, 73102 }, + { 73107, 73108 }, + { 73110, 73110 }, + { 73461, 73462 }, { 94033, 94078 }, { 119141, 119142 }, { 119149, 119154 }, @@ -2543,12 +2585,13 @@ { 1840, 1866 }, { 1958, 1968 }, { 2027, 2035 }, + { 2045, 2045 }, { 2070, 2073 }, { 2075, 2083 }, { 2085, 2087 }, { 2089, 2093 }, { 2137, 2139 }, - { 2260, 2273 }, + { 2259, 2273 }, { 2275, 2306 }, { 2362, 2362 }, { 2364, 2364 }, @@ -2561,6 +2604,7 @@ { 2497, 2500 }, { 2509, 2509 }, { 2530, 2531 }, + { 2558, 2558 }, { 2561, 2562 }, { 2620, 2620 }, { 2625, 2626 }, @@ -2587,6 +2631,7 @@ { 3008, 3008 }, { 3021, 3021 }, { 3072, 3072 }, + { 3076, 3076 }, { 3134, 3136 }, { 3142, 3144 }, { 3146, 3149 }, @@ -2703,6 +2748,7 @@ { 43045, 43046 }, { 43204, 43205 }, { 43232, 43249 }, + { 43263, 43263 }, { 43302, 43309 }, { 43335, 43345 }, { 43392, 43394 }, @@ -2740,6 +2786,8 @@ { 68152, 68154 }, { 68159, 68159 }, { 68325, 68326 }, + { 68900, 68903 }, + { 69446, 69456 }, { 69633, 69633 }, { 69688, 69702 }, { 69759, 69761 }, @@ -2751,7 +2799,7 @@ { 70003, 70003 }, { 70016, 70017 }, { 70070, 70078 }, - { 70090, 70092 }, + { 70089, 70092 }, { 70191, 70193 }, { 70196, 70196 }, { 70198, 70199 }, @@ -2759,13 +2807,14 @@ { 70367, 70367 }, { 70371, 70378 }, { 70400, 70401 }, - { 70460, 70460 }, + { 70459, 70460 }, { 70464, 70464 }, { 70502, 70508 }, { 70512, 70516 }, { 70712, 70719 }, { 70722, 70724 }, { 70726, 70726 }, + { 70750, 70750 }, { 70835, 70840 }, { 70842, 70842 }, { 70847, 70848 }, @@ -2784,8 +2833,9 @@ { 71453, 71455 }, { 71458, 71461 }, { 71463, 71467 }, - { 72193, 72198 }, - { 72201, 72202 }, + { 71727, 71735 }, + { 71737, 71738 }, + { 72193, 72202 }, { 72243, 72248 }, { 72251, 72254 }, { 72263, 72263 }, @@ -2805,6 +2855,10 @@ { 73020, 73021 }, { 73023, 73029 }, { 73031, 73031 }, + { 73104, 73105 }, + { 73109, 73109 }, + { 73111, 73111 }, + { 73459, 73460 }, { 92912, 92916 }, { 92976, 92982 }, { 94095, 94098 }, @@ -2848,12 +2902,13 @@ { 1840, 1866 }, { 1958, 1968 }, { 2027, 2035 }, + { 2045, 2045 }, { 2070, 2073 }, { 2075, 2083 }, { 2085, 2087 }, { 2089, 2093 }, { 2137, 2139 }, - { 2260, 2273 }, + { 2259, 2273 }, { 2275, 2307 }, { 2362, 2364 }, { 2366, 2383 }, @@ -2866,6 +2921,7 @@ { 2507, 2509 }, { 2519, 2519 }, { 2530, 2531 }, + { 2558, 2558 }, { 2561, 2563 }, { 2620, 2620 }, { 2622, 2626 }, @@ -2893,7 +2949,7 @@ { 3014, 3016 }, { 3018, 3021 }, { 3031, 3031 }, - { 3072, 3075 }, + { 3072, 3076 }, { 3134, 3140 }, { 3142, 3144 }, { 3146, 3149 }, @@ -2993,6 +3049,7 @@ { 43136, 43137 }, { 43188, 43205 }, { 43232, 43249 }, + { 43263, 43263 }, { 43302, 43309 }, { 43335, 43347 }, { 43392, 43395 }, @@ -3025,21 +3082,24 @@ { 68152, 68154 }, { 68159, 68159 }, { 68325, 68326 }, + { 68900, 68903 }, + { 69446, 69456 }, { 69632, 69634 }, { 69688, 69702 }, { 69759, 69762 }, { 69808, 69818 }, { 69888, 69890 }, { 69927, 69940 }, + { 69957, 69958 }, { 70003, 70003 }, { 70016, 70018 }, { 70067, 70080 }, - { 70090, 70092 }, + { 70089, 70092 }, { 70188, 70199 }, { 70206, 70206 }, { 70367, 70378 }, { 70400, 70403 }, - { 70460, 70460 }, + { 70459, 70460 }, { 70462, 70468 }, { 70471, 70472 }, { 70475, 70477 }, @@ -3048,6 +3108,7 @@ { 70502, 70508 }, { 70512, 70516 }, { 70709, 70726 }, + { 70750, 70750 }, { 70832, 70851 }, { 71087, 71093 }, { 71096, 71104 }, @@ -3055,6 +3116,7 @@ { 71216, 71232 }, { 71339, 71351 }, { 71453, 71467 }, + { 71724, 71738 }, { 72193, 72202 }, { 72243, 72249 }, { 72251, 72254 }, @@ -3070,6 +3132,10 @@ { 73020, 73021 }, { 73023, 73029 }, { 73031, 73031 }, + { 73098, 73102 }, + { 73104, 73105 }, + { 73107, 73111 }, + { 73459, 73462 }, { 92912, 92916 }, { 92976, 92982 }, { 94033, 94078 }, @@ -3122,9 +3188,9 @@ { 1162, 1327 }, { 1329, 1366 }, { 1369, 1369 }, - { 1377, 1415 }, + { 1376, 1416 }, { 1488, 1514 }, - { 1520, 1522 }, + { 1519, 1522 }, { 1568, 1610 }, { 1646, 1647 }, { 1649, 1747 }, @@ -3306,7 +3372,7 @@ { 6016, 6067 }, { 6103, 6103 }, { 6108, 6108 }, - { 6176, 6263 }, + { 6176, 6264 }, { 6272, 6276 }, { 6279, 6312 }, { 6314, 6314 }, @@ -3328,6 +3394,8 @@ { 7245, 7247 }, { 7258, 7293 }, { 7296, 7304 }, + { 7312, 7354 }, + { 7357, 7359 }, { 7401, 7404 }, { 7406, 7409 }, { 7413, 7414 }, @@ -3395,12 +3463,12 @@ { 12445, 12447 }, { 12449, 12538 }, { 12540, 12543 }, - { 12549, 12590 }, + { 12549, 12591 }, { 12593, 12686 }, { 12704, 12730 }, { 12784, 12799 }, { 13312, 19893 }, - { 19968, 40938 }, + { 19968, 40943 }, { 40960, 42124 }, { 42192, 42237 }, { 42240, 42508 }, @@ -3411,8 +3479,7 @@ { 42656, 42725 }, { 42775, 42783 }, { 42786, 42888 }, - { 42891, 42926 }, - { 42928, 42935 }, + { 42891, 42937 }, { 42999, 43009 }, { 43011, 43013 }, { 43015, 43018 }, @@ -3421,7 +3488,7 @@ { 43138, 43187 }, { 43250, 43255 }, { 43259, 43259 }, - { 43261, 43261 }, + { 43261, 43262 }, { 43274, 43301 }, { 43312, 43334 }, { 43360, 43388 }, @@ -3523,7 +3590,7 @@ { 68096, 68096 }, { 68112, 68115 }, { 68117, 68119 }, - { 68121, 68147 }, + { 68121, 68149 }, { 68192, 68220 }, { 68224, 68252 }, { 68288, 68295 }, @@ -3535,10 +3602,15 @@ { 68608, 68680 }, { 68736, 68786 }, { 68800, 68850 }, + { 68864, 68899 }, + { 69376, 69404 }, + { 69415, 69415 }, + { 69424, 69445 }, { 69635, 69687 }, { 69763, 69807 }, { 69840, 69864 }, { 69891, 69926 }, + { 69956, 69956 }, { 69968, 70002 }, { 70006, 70006 }, { 70019, 70066 }, @@ -3572,7 +3644,8 @@ { 71168, 71215 }, { 71236, 71236 }, { 71296, 71338 }, - { 71424, 71449 }, + { 71424, 71450 }, + { 71680, 71723 }, { 71840, 71903 }, { 71935, 71935 }, { 72192, 72192 }, @@ -3581,6 +3654,7 @@ { 72272, 72272 }, { 72284, 72323 }, { 72326, 72329 }, + { 72349, 72349 }, { 72384, 72440 }, { 72704, 72712 }, { 72714, 72750 }, @@ -3590,6 +3664,11 @@ { 72968, 72969 }, { 72971, 73008 }, { 73030, 73030 }, + { 73056, 73061 }, + { 73063, 73064 }, + { 73066, 73097 }, + { 73112, 73112 }, + { 73440, 73458 }, { 73728, 74649 }, { 74880, 75075 }, { 77824, 78894 }, @@ -3601,11 +3680,12 @@ { 92992, 92995 }, { 93027, 93047 }, { 93053, 93071 }, + { 93760, 93823 }, { 93952, 94020 }, { 94032, 94032 }, { 94099, 94111 }, { 94176, 94177 }, - { 94208, 100332 }, + { 94208, 100337 }, { 100352, 101106 }, { 110592, 110878 }, { 110960, 111355 }, @@ -3772,7 +3852,7 @@ { 68028, 68029 }, { 68032, 68047 }, { 68050, 68095 }, - { 68160, 68167 }, + { 68160, 68168 }, { 68221, 68222 }, { 68253, 68255 }, { 68331, 68335 }, @@ -3780,7 +3860,10 @@ { 68472, 68479 }, { 68521, 68527 }, { 68858, 68863 }, + { 68912, 68921 }, { 69216, 69246 }, + { 69405, 69414 }, + { 69457, 69460 }, { 69714, 69743 }, { 69872, 69881 }, { 69942, 69951 }, @@ -3795,14 +3878,20 @@ { 71904, 71922 }, { 72784, 72812 }, { 73040, 73049 }, + { 73120, 73129 }, { 74752, 74862 }, { 92768, 92777 }, { 93008, 93017 }, { 93019, 93025 }, - { 119648, 119665 }, + { 93824, 93846 }, + { 119520, 119539 }, + { 119648, 119672 }, { 120782, 120831 }, { 125127, 125135 }, { 125264, 125273 }, + { 126065, 126123 }, + { 126125, 126127 }, + { 126129, 126132 }, { 127232, 127244 }, }; static const URange16 Sk_range16[] = { @@ -3876,7 +3965,9 @@ { 2404, 2405 }, { 2416, 2416 }, { 2557, 2557 }, + { 2678, 2678 }, { 2800, 2800 }, + { 3204, 3204 }, { 3572, 3572 }, { 3663, 3663 }, { 3674, 3675 }, @@ -3925,7 +4016,7 @@ { 11518, 11519 }, { 11632, 11632 }, { 11776, 11822 }, - { 11824, 11849 }, + { 11824, 11854 }, { 12289, 12291 }, { 12296, 12305 }, { 12308, 12319 }, @@ -3981,12 +4072,13 @@ { 68336, 68342 }, { 68409, 68415 }, { 68505, 68508 }, + { 69461, 69465 }, { 69703, 69709 }, { 69819, 69820 }, { 69822, 69825 }, { 69952, 69955 }, { 70004, 70005 }, - { 70085, 70089 }, + { 70085, 70088 }, { 70093, 70093 }, { 70107, 70107 }, { 70109, 70111 }, @@ -4000,16 +4092,19 @@ { 71233, 71235 }, { 71264, 71276 }, { 71484, 71486 }, + { 71739, 71739 }, { 72255, 72262 }, { 72346, 72348 }, { 72350, 72354 }, { 72769, 72773 }, { 72816, 72817 }, + { 73463, 73464 }, { 74864, 74868 }, { 92782, 92783 }, { 92917, 92917 }, { 92983, 92987 }, { 92996, 92996 }, + { 93847, 93850 }, { 113823, 113823 }, { 121479, 121483 }, { 125278, 125279 }, @@ -4047,6 +4142,7 @@ { 1769, 1769 }, { 1789, 1790 }, { 2038, 2038 }, + { 2046, 2047 }, { 2546, 2547 }, { 2554, 2555 }, { 2801, 2801 }, @@ -4113,10 +4209,8 @@ { 10716, 10747 }, { 10750, 11123 }, { 11126, 11157 }, - { 11160, 11193 }, - { 11197, 11208 }, - { 11210, 11218 }, - { 11244, 11247 }, + { 11160, 11208 }, + { 11210, 11262 }, { 11493, 11498 }, { 11904, 11929 }, { 11931, 12019 }, @@ -4202,6 +4296,8 @@ { 121453, 121460 }, { 121462, 121475 }, { 121477, 121478 }, + { 126124, 126124 }, + { 126128, 126128 }, { 126704, 126705 }, { 126976, 127019 }, { 127024, 127123 }, @@ -4209,8 +4305,7 @@ { 127153, 127167 }, { 127169, 127183 }, { 127185, 127221 }, - { 127248, 127278 }, - { 127280, 127339 }, + { 127248, 127339 }, { 127344, 127404 }, { 127462, 127490 }, { 127504, 127547 }, @@ -4219,9 +4314,9 @@ { 127584, 127589 }, { 127744, 128724 }, { 128736, 128748 }, - { 128752, 128760 }, + { 128752, 128761 }, { 128768, 128883 }, - { 128896, 128980 }, + { 128896, 128984 }, { 129024, 129035 }, { 129040, 129095 }, { 129104, 129113 }, @@ -4229,11 +4324,14 @@ { 129168, 129197 }, { 129280, 129291 }, { 129296, 129342 }, - { 129344, 129356 }, - { 129360, 129387 }, - { 129408, 129431 }, - { 129472, 129472 }, - { 129488, 129510 }, + { 129344, 129392 }, + { 129395, 129398 }, + { 129402, 129402 }, + { 129404, 129442 }, + { 129456, 129465 }, + { 129472, 129474 }, + { 129488, 129535 }, + { 129632, 129645 }, }; static const URange16 So_range16[] = { { 166, 166 }, @@ -4315,10 +4413,8 @@ { 11077, 11078 }, { 11085, 11123 }, { 11126, 11157 }, - { 11160, 11193 }, - { 11197, 11208 }, - { 11210, 11218 }, - { 11244, 11247 }, + { 11160, 11208 }, + { 11210, 11262 }, { 11493, 11498 }, { 11904, 11929 }, { 11931, 12019 }, @@ -4379,14 +4475,14 @@ { 121453, 121460 }, { 121462, 121475 }, { 121477, 121478 }, + { 126124, 126124 }, { 126976, 127019 }, { 127024, 127123 }, { 127136, 127150 }, { 127153, 127167 }, { 127169, 127183 }, { 127185, 127221 }, - { 127248, 127278 }, - { 127280, 127339 }, + { 127248, 127339 }, { 127344, 127404 }, { 127462, 127490 }, { 127504, 127547 }, @@ -4396,9 +4492,9 @@ { 127744, 127994 }, { 128000, 128724 }, { 128736, 128748 }, - { 128752, 128760 }, + { 128752, 128761 }, { 128768, 128883 }, - { 128896, 128980 }, + { 128896, 128984 }, { 129024, 129035 }, { 129040, 129095 }, { 129104, 129113 }, @@ -4406,11 +4502,14 @@ { 129168, 129197 }, { 129280, 129291 }, { 129296, 129342 }, - { 129344, 129356 }, - { 129360, 129387 }, - { 129408, 129431 }, - { 129472, 129472 }, - { 129488, 129510 }, + { 129344, 129392 }, + { 129395, 129398 }, + { 129402, 129402 }, + { 129404, 129442 }, + { 129456, 129465 }, + { 129472, 129474 }, + { 129488, 129535 }, + { 129632, 129645 }, }; static const URange16 Sm_range16[] = { { 43, 43 }, @@ -4485,6 +4584,7 @@ { 162, 165 }, { 1423, 1423 }, { 1547, 1547 }, + { 2046, 2047 }, { 2546, 2547 }, { 2555, 2555 }, { 2801, 2801 }, @@ -4499,6 +4599,9 @@ { 65504, 65505 }, { 65509, 65510 }, }; +static const URange32 Sc_range32[] = { + { 126128, 126128 }, +}; static const URange16 Z_range16[] = { { 32, 32 }, { 160, 160 }, @@ -4540,6 +4643,7 @@ }; static const URange32 Cf_range32[] = { { 69821, 69821 }, + { 69837, 69837 }, { 113824, 113827 }, { 119155, 119162 }, { 917505, 917505 }, @@ -4562,7 +4666,7 @@ }; static const URange32 Tangut_range32[] = { { 94176, 94176 }, - { 94208, 100332 }, + { 94208, 100337 }, { 100352, 101106 }, }; static const URange16 Thaana_range16[] = { @@ -4574,8 +4678,7 @@ { 125278, 125279 }, }; static const URange16 Telugu_range16[] = { - { 3072, 3075 }, - { 3077, 3084 }, + { 3072, 3084 }, { 3086, 3088 }, { 3090, 3112 }, { 3114, 3129 }, @@ -4679,6 +4782,7 @@ static const URange32 Inherited_range32[] = { { 66045, 66045 }, { 66272, 66272 }, + { 70459, 70459 }, { 119143, 119145 }, { 119163, 119170 }, { 119173, 119179 }, @@ -4697,7 +4801,7 @@ { 72784, 72812 }, }; static const URange32 Ahom_range32[] = { - { 71424, 71449 }, + { 71424, 71450 }, { 71453, 71467 }, { 71472, 71487 }, }; @@ -4710,7 +4814,7 @@ { 12321, 12329 }, { 12344, 12347 }, { 13312, 19893 }, - { 19968, 40938 }, + { 19968, 40943 }, { 63744, 64109 }, { 64112, 64217 }, }; @@ -4727,8 +4831,7 @@ }; static const URange16 Armenian_range16[] = { { 1329, 1366 }, - { 1369, 1375 }, - { 1377, 1415 }, + { 1369, 1416 }, { 1418, 1418 }, { 1421, 1423 }, { 64275, 64279 }, @@ -4753,7 +4856,7 @@ }; static const URange16 Bopomofo_range16[] = { { 746, 747 }, - { 12549, 12590 }, + { 12549, 12591 }, { 12704, 12730 }, }; static const URange32 Bassa_Vah_range32[] = { @@ -4768,6 +4871,9 @@ { 66736, 66771 }, { 66776, 66811 }, }; +static const URange32 Old_Sogdian_range32[] = { + { 69376, 69415 }, +}; static const URange16 Tagalog_range16[] = { { 5888, 5900 }, { 5902, 5908 }, @@ -4808,6 +4914,10 @@ { 43968, 44013 }, { 44016, 44025 }, }; +static const URange32 Hanifi_Rohingya_range32[] = { + { 68864, 68903 }, + { 68912, 68921 }, +}; static const URange32 Pahawh_Hmong_range32[] = { { 92928, 92997 }, { 93008, 93017 }, @@ -4832,9 +4942,9 @@ { 68101, 68102 }, { 68108, 68115 }, { 68117, 68119 }, - { 68121, 68147 }, + { 68121, 68149 }, { 68152, 68154 }, - { 68159, 68167 }, + { 68159, 68168 }, { 68176, 68184 }, }; static const URange16 Tai_Tham_range16[] = { @@ -4880,8 +4990,7 @@ { 8544, 8584 }, { 11360, 11391 }, { 42786, 42887 }, - { 42891, 42926 }, - { 42928, 42935 }, + { 42891, 42937 }, { 42999, 43007 }, { 43824, 43866 }, { 43868, 43876 }, @@ -4902,6 +5011,8 @@ { 4301, 4301 }, { 4304, 4346 }, { 4348, 4351 }, + { 7312, 7354 }, + { 7357, 7359 }, { 11520, 11557 }, { 11559, 11559 }, { 11565, 11565 }, @@ -4938,7 +5049,7 @@ { 2304, 2384 }, { 2387, 2403 }, { 2406, 2431 }, - { 43232, 43261 }, + { 43232, 43263 }, }; static const URange16 Thai_range16[] = { { 3585, 3642 }, @@ -5079,7 +5190,7 @@ static const URange32 Newa_range32[] = { { 70656, 70745 }, { 70747, 70747 }, - { 70749, 70749 }, + { 70749, 70750 }, }; static const URange16 Limbu_range16[] = { { 6400, 6430 }, @@ -5117,6 +5228,9 @@ { 2911, 2915 }, { 2918, 2935 }, }; +static const URange32 Medefaidrin_range32[] = { + { 93760, 93850 }, +}; static const URange32 Sharada_range32[] = { { 70016, 70093 }, { 70096, 70111 }, @@ -5145,6 +5259,14 @@ { 71168, 71236 }, { 71248, 71257 }, }; +static const URange32 Gunjala_Gondi_range32[] = { + { 73056, 73061 }, + { 73063, 73064 }, + { 73066, 73102 }, + { 73104, 73105 }, + { 73107, 73112 }, + { 73120, 73129 }, +}; static const URange32 Inscriptional_Pahlavi_range32[] = { { 68448, 68466 }, { 68472, 68479 }, @@ -5183,6 +5305,7 @@ }; static const URange16 Nko_range16[] = { { 1984, 2042 }, + { 2045, 2047 }, }; static const URange16 Canadian_Aboriginal_range16[] = { { 5120, 5759 }, @@ -5213,10 +5336,11 @@ { 2519, 2519 }, { 2524, 2525 }, { 2527, 2531 }, - { 2534, 2557 }, + { 2534, 2558 }, }; static const URange32 Kaithi_range32[] = { { 69760, 69825 }, + { 69837, 69837 }, }; static const URange16 Glagolitic_range16[] = { { 11264, 11310 }, @@ -5253,7 +5377,7 @@ { 2641, 2641 }, { 2649, 2652 }, { 2654, 2654 }, - { 2662, 2677 }, + { 2662, 2678 }, }; static const URange16 Javanese_range16[] = { { 43392, 43469 }, @@ -5275,8 +5399,7 @@ { 67647, 67647 }, }; static const URange16 Kannada_range16[] = { - { 3200, 3203 }, - { 3205, 3212 }, + { 3200, 3212 }, { 3214, 3216 }, { 3218, 3240 }, { 3242, 3251 }, @@ -5299,7 +5422,7 @@ { 6148, 6148 }, { 6150, 6158 }, { 6160, 6169 }, - { 6176, 6263 }, + { 6176, 6264 }, { 6272, 6314 }, }; static const URange32 Mongolian_range32[] = { @@ -5403,6 +5526,9 @@ { 67392, 67413 }, { 67424, 67431 }, }; +static const URange32 Dogra_range32[] = { + { 71680, 71739 }, +}; static const URange32 Old_Turkic_range32[] = { { 68608, 68680 }, }; @@ -5418,10 +5544,16 @@ static const URange32 Egyptian_Hieroglyphs_range32[] = { { 77824, 78894 }, }; +static const URange32 Sogdian_range32[] = { + { 69424, 69465 }, +}; static const URange32 Caucasian_Albanian_range32[] = { { 66864, 66915 }, { 66927, 66927 }, }; +static const URange32 Makasar_range32[] = { + { 73440, 73464 }, +}; static const URange32 Old_Hungarian_range32[] = { { 68736, 68786 }, { 68800, 68850 }, @@ -5502,11 +5634,9 @@ { 9312, 10239 }, { 10496, 11123 }, { 11126, 11157 }, - { 11160, 11193 }, - { 11197, 11208 }, - { 11210, 11218 }, - { 11244, 11247 }, - { 11776, 11849 }, + { 11160, 11208 }, + { 11210, 11262 }, + { 11776, 11854 }, { 12272, 12283 }, { 12288, 12292 }, { 12294, 12294 }, @@ -5558,8 +5688,9 @@ { 119171, 119172 }, { 119180, 119209 }, { 119214, 119272 }, + { 119520, 119539 }, { 119552, 119638 }, - { 119648, 119665 }, + { 119648, 119672 }, { 119808, 119892 }, { 119894, 119964 }, { 119966, 119967 }, @@ -5581,6 +5712,7 @@ { 120146, 120485 }, { 120488, 120779 }, { 120782, 120831 }, + { 126065, 126132 }, { 126976, 127019 }, { 127024, 127123 }, { 127136, 127150 }, @@ -5588,8 +5720,7 @@ { 127169, 127183 }, { 127185, 127221 }, { 127232, 127244 }, - { 127248, 127278 }, - { 127280, 127339 }, + { 127248, 127339 }, { 127344, 127404 }, { 127462, 127487 }, { 127489, 127490 }, @@ -5599,9 +5730,9 @@ { 127584, 127589 }, { 127744, 128724 }, { 128736, 128748 }, - { 128752, 128760 }, + { 128752, 128761 }, { 128768, 128883 }, - { 128896, 128980 }, + { 128896, 128984 }, { 129024, 129035 }, { 129040, 129095 }, { 129104, 129113 }, @@ -5609,11 +5740,14 @@ { 129168, 129197 }, { 129280, 129291 }, { 129296, 129342 }, - { 129344, 129356 }, - { 129360, 129387 }, - { 129408, 129431 }, - { 129472, 129472 }, - { 129488, 129510 }, + { 129344, 129392 }, + { 129395, 129398 }, + { 129402, 129402 }, + { 129404, 129442 }, + { 129456, 129465 }, + { 129472, 129474 }, + { 129488, 129535 }, + { 129632, 129645 }, { 917505, 917505 }, { 917536, 917631 }, }; @@ -5624,7 +5758,7 @@ }; static const URange32 Chakma_range32[] = { { 69888, 69940 }, - { 69942, 69955 }, + { 69942, 69958 }, }; static const URange16 Arabic_range16[] = { { 1536, 1540 }, @@ -5640,7 +5774,7 @@ { 1872, 1919 }, { 2208, 2228 }, { 2230, 2237 }, - { 2260, 2273 }, + { 2259, 2273 }, { 2275, 2303 }, { 64336, 64449 }, { 64467, 64829 }, @@ -5704,8 +5838,7 @@ }; static const URange32 Soyombo_range32[] = { { 72272, 72323 }, - { 72326, 72348 }, - { 72350, 72354 }, + { 72326, 72354 }, }; static const URange32 Avestan_range32[] = { { 68352, 68405 }, @@ -5714,7 +5847,7 @@ static const URange16 Hebrew_range16[] = { { 1425, 1479 }, { 1488, 1514 }, - { 1520, 1524 }, + { 1519, 1524 }, { 64285, 64310 }, { 64312, 64316 }, { 64318, 64318 }, @@ -5731,13 +5864,13 @@ { 71296, 71351 }, { 71360, 71369 }, }; -// 3981 16-bit ranges, 1325 32-bit ranges +// 3994 16-bit ranges, 1429 32-bit ranges const UGroup unicode_groups[] = { { "Adlam", +1, 0, 0, Adlam_range32, 3 }, { "Ahom", +1, 0, 0, Ahom_range32, 3 }, { "Anatolian_Hieroglyphs", +1, 0, 0, Anatolian_Hieroglyphs_range32, 1 }, { "Arabic", +1, Arabic_range16, 22, Arabic_range32, 35 }, - { "Armenian", +1, Armenian_range16, 6, 0, 0 }, + { "Armenian", +1, Armenian_range16, 5, 0, 0 }, { "Avestan", +1, 0, 0, Avestan_range32, 2 }, { "Balinese", +1, Balinese_range16, 2, 0, 0 }, { "Bamum", +1, Bamum_range16, 1, Bamum_range32, 1 }, @@ -5750,17 +5883,17 @@ { "Braille", +1, Braille_range16, 1, 0, 0 }, { "Buginese", +1, Buginese_range16, 2, 0, 0 }, { "Buhid", +1, Buhid_range16, 1, 0, 0 }, - { "C", +1, C_range16, 16, C_range32, 7 }, + { "C", +1, C_range16, 16, C_range32, 8 }, { "Canadian_Aboriginal", +1, Canadian_Aboriginal_range16, 2, 0, 0 }, { "Carian", +1, 0, 0, Carian_range32, 1 }, { "Caucasian_Albanian", +1, 0, 0, Caucasian_Albanian_range32, 2 }, { "Cc", +1, Cc_range16, 2, 0, 0 }, - { "Cf", +1, Cf_range16, 13, Cf_range32, 5 }, + { "Cf", +1, Cf_range16, 13, Cf_range32, 6 }, { "Chakma", +1, 0, 0, Chakma_range32, 2 }, { "Cham", +1, Cham_range16, 4, 0, 0 }, { "Cherokee", +1, Cherokee_range16, 3, 0, 0 }, { "Co", +1, Co_range16, 1, Co_range32, 2 }, - { "Common", +1, Common_range16, 92, Common_range32, 72 }, + { "Common", +1, Common_range16, 90, Common_range32, 76 }, { "Coptic", +1, Coptic_range16, 3, 0, 0 }, { "Cs", +1, Cs_range16, 1, 0, 0 }, { "Cuneiform", +1, 0, 0, Cuneiform_range32, 4 }, @@ -5768,79 +5901,84 @@ { "Cyrillic", +1, Cyrillic_range16, 8, 0, 0 }, { "Deseret", +1, 0, 0, Deseret_range32, 1 }, { "Devanagari", +1, Devanagari_range16, 4, 0, 0 }, + { "Dogra", +1, 0, 0, Dogra_range32, 1 }, { "Duployan", +1, 0, 0, Duployan_range32, 5 }, { "Egyptian_Hieroglyphs", +1, 0, 0, Egyptian_Hieroglyphs_range32, 1 }, { "Elbasan", +1, 0, 0, Elbasan_range32, 1 }, { "Ethiopic", +1, Ethiopic_range16, 32, 0, 0 }, - { "Georgian", +1, Georgian_range16, 8, 0, 0 }, + { "Georgian", +1, Georgian_range16, 10, 0, 0 }, { "Glagolitic", +1, Glagolitic_range16, 2, Glagolitic_range32, 5 }, { "Gothic", +1, 0, 0, Gothic_range32, 1 }, { "Grantha", +1, 0, 0, Grantha_range32, 15 }, { "Greek", +1, Greek_range16, 33, Greek_range32, 3 }, { "Gujarati", +1, Gujarati_range16, 14, 0, 0 }, + { "Gunjala_Gondi", +1, 0, 0, Gunjala_Gondi_range32, 6 }, { "Gurmukhi", +1, Gurmukhi_range16, 16, 0, 0 }, { "Han", +1, Han_range16, 11, Han_range32, 6 }, { "Hangul", +1, Hangul_range16, 14, 0, 0 }, + { "Hanifi_Rohingya", +1, 0, 0, Hanifi_Rohingya_range32, 2 }, { "Hanunoo", +1, Hanunoo_range16, 1, 0, 0 }, { "Hatran", +1, 0, 0, Hatran_range32, 3 }, { "Hebrew", +1, Hebrew_range16, 9, 0, 0 }, { "Hiragana", +1, Hiragana_range16, 2, Hiragana_range32, 2 }, { "Imperial_Aramaic", +1, 0, 0, Imperial_Aramaic_range32, 2 }, - { "Inherited", +1, Inherited_range16, 20, Inherited_range32, 7 }, + { "Inherited", +1, Inherited_range16, 20, Inherited_range32, 8 }, { "Inscriptional_Pahlavi", +1, 0, 0, Inscriptional_Pahlavi_range32, 2 }, { "Inscriptional_Parthian", +1, 0, 0, Inscriptional_Parthian_range32, 2 }, { "Javanese", +1, Javanese_range16, 3, 0, 0 }, - { "Kaithi", +1, 0, 0, Kaithi_range32, 1 }, - { "Kannada", +1, Kannada_range16, 14, 0, 0 }, + { "Kaithi", +1, 0, 0, Kaithi_range32, 2 }, + { "Kannada", +1, Kannada_range16, 13, 0, 0 }, { "Katakana", +1, Katakana_range16, 7, Katakana_range32, 1 }, { "Kayah_Li", +1, Kayah_Li_range16, 2, 0, 0 }, { "Kharoshthi", +1, 0, 0, Kharoshthi_range32, 8 }, { "Khmer", +1, Khmer_range16, 4, 0, 0 }, { "Khojki", +1, 0, 0, Khojki_range32, 2 }, { "Khudawadi", +1, 0, 0, Khudawadi_range32, 2 }, - { "L", +1, L_range16, 383, L_range32, 202 }, + { "L", +1, L_range16, 384, L_range32, 215 }, { "Lao", +1, Lao_range16, 18, 0, 0 }, - { "Latin", +1, Latin_range16, 31, 0, 0 }, + { "Latin", +1, Latin_range16, 30, 0, 0 }, { "Lepcha", +1, Lepcha_range16, 3, 0, 0 }, { "Limbu", +1, Limbu_range16, 5, 0, 0 }, { "Linear_A", +1, 0, 0, Linear_A_range32, 3 }, { "Linear_B", +1, 0, 0, Linear_B_range32, 7 }, { "Lisu", +1, Lisu_range16, 1, 0, 0 }, - { "Ll", +1, Ll_range16, 600, Ll_range32, 33 }, + { "Ll", +1, Ll_range16, 604, Ll_range32, 34 }, { "Lm", +1, Lm_range16, 54, Lm_range32, 3 }, - { "Lo", +1, Lo_range16, 296, Lo_range32, 163 }, + { "Lo", +1, Lo_range16, 295, Lo_range32, 175 }, { "Lt", +1, Lt_range16, 10, 0, 0 }, - { "Lu", +1, Lu_range16, 591, Lu_range32, 36 }, + { "Lu", +1, Lu_range16, 594, Lu_range32, 37 }, { "Lycian", +1, 0, 0, Lycian_range32, 1 }, { "Lydian", +1, 0, 0, Lydian_range32, 2 }, - { "M", +1, M_range16, 184, M_range32, 79 }, + { "M", +1, M_range16, 187, M_range32, 88 }, { "Mahajani", +1, 0, 0, Mahajani_range32, 1 }, + { "Makasar", +1, 0, 0, Makasar_range32, 1 }, { "Malayalam", +1, Malayalam_range16, 8, 0, 0 }, { "Mandaic", +1, Mandaic_range16, 2, 0, 0 }, { "Manichaean", +1, 0, 0, Manichaean_range32, 2 }, { "Marchen", +1, 0, 0, Marchen_range32, 3 }, { "Masaram_Gondi", +1, 0, 0, Masaram_Gondi_range32, 7 }, - { "Mc", +1, Mc_range16, 110, Mc_range32, 50 }, + { "Mc", +1, Mc_range16, 110, Mc_range32, 56 }, { "Me", +1, Me_range16, 5, 0, 0 }, + { "Medefaidrin", +1, 0, 0, Medefaidrin_range32, 1 }, { "Meetei_Mayek", +1, Meetei_Mayek_range16, 3, 0, 0 }, { "Mende_Kikakui", +1, 0, 0, Mende_Kikakui_range32, 2 }, { "Meroitic_Cursive", +1, 0, 0, Meroitic_Cursive_range32, 3 }, { "Meroitic_Hieroglyphs", +1, 0, 0, Meroitic_Hieroglyphs_range32, 1 }, { "Miao", +1, 0, 0, Miao_range32, 3 }, - { "Mn", +1, Mn_range16, 204, Mn_range32, 97 }, + { "Mn", +1, Mn_range16, 208, Mn_range32, 105 }, { "Modi", +1, 0, 0, Modi_range32, 2 }, { "Mongolian", +1, Mongolian_range16, 6, Mongolian_range32, 1 }, { "Mro", +1, 0, 0, Mro_range32, 3 }, { "Multani", +1, 0, 0, Multani_range32, 5 }, { "Myanmar", +1, Myanmar_range16, 3, 0, 0 }, - { "N", +1, N_range16, 67, N_range32, 49 }, + { "N", +1, N_range16, 67, N_range32, 58 }, { "Nabataean", +1, 0, 0, Nabataean_range32, 2 }, - { "Nd", +1, Nd_range16, 37, Nd_range32, 18 }, + { "Nd", +1, Nd_range16, 37, Nd_range32, 20 }, { "New_Tai_Lue", +1, New_Tai_Lue_range16, 4, 0, 0 }, { "Newa", +1, 0, 0, Newa_range32, 3 }, - { "Nko", +1, Nko_range16, 1, 0, 0 }, + { "Nko", +1, Nko_range16, 2, 0, 0 }, { "Nl", +1, Nl_range16, 7, Nl_range32, 5 }, - { "No", +1, No_range16, 29, No_range32, 31 }, + { "No", +1, No_range16, 29, No_range32, 38 }, { "Nushu", +1, 0, 0, Nushu_range32, 2 }, { "Ogham", +1, Ogham_range16, 1, 0, 0 }, { "Ol_Chiki", +1, Ol_Chiki_range16, 1, 0, 0 }, @@ -5849,12 +5987,13 @@ { "Old_North_Arabian", +1, 0, 0, Old_North_Arabian_range32, 1 }, { "Old_Permic", +1, 0, 0, Old_Permic_range32, 1 }, { "Old_Persian", +1, 0, 0, Old_Persian_range32, 2 }, + { "Old_Sogdian", +1, 0, 0, Old_Sogdian_range32, 1 }, { "Old_South_Arabian", +1, 0, 0, Old_South_Arabian_range32, 1 }, { "Old_Turkic", +1, 0, 0, Old_Turkic_range32, 1 }, { "Oriya", +1, Oriya_range16, 14, 0, 0 }, { "Osage", +1, 0, 0, Osage_range32, 2 }, { "Osmanya", +1, 0, 0, Osmanya_range32, 2 }, - { "P", +1, P_range16, 128, P_range32, 44 }, + { "P", +1, P_range16, 130, P_range32, 48 }, { "Pahawh_Hmong", +1, 0, 0, Pahawh_Hmong_range32, 5 }, { "Palmyrene", +1, 0, 0, Palmyrene_range32, 1 }, { "Pau_Cin_Hau", +1, 0, 0, Pau_Cin_Hau_range32, 1 }, @@ -5865,15 +6004,15 @@ { "Phags_Pa", +1, Phags_Pa_range16, 1, 0, 0 }, { "Phoenician", +1, 0, 0, Phoenician_range32, 2 }, { "Pi", +1, Pi_range16, 11, 0, 0 }, - { "Po", +1, Po_range16, 125, Po_range32, 44 }, + { "Po", +1, Po_range16, 127, Po_range32, 48 }, { "Ps", +1, Ps_range16, 75, 0, 0 }, { "Psalter_Pahlavi", +1, 0, 0, Psalter_Pahlavi_range32, 3 }, { "Rejang", +1, Rejang_range16, 2, 0, 0 }, { "Runic", +1, Runic_range16, 2, 0, 0 }, - { "S", +1, S_range16, 148, S_range32, 69 }, + { "S", +1, S_range16, 147, S_range32, 73 }, { "Samaritan", +1, Samaritan_range16, 2, 0, 0 }, { "Saurashtra", +1, Saurashtra_range16, 2, 0, 0 }, - { "Sc", +1, Sc_range16, 17, 0, 0 }, + { "Sc", +1, Sc_range16, 18, Sc_range32, 1 }, { "Sharada", +1, 0, 0, Sharada_range32, 2 }, { "Shavian", +1, 0, 0, Shavian_range32, 1 }, { "Siddham", +1, 0, 0, Siddham_range32, 2 }, @@ -5881,9 +6020,10 @@ { "Sinhala", +1, Sinhala_range16, 12, Sinhala_range32, 1 }, { "Sk", +1, Sk_range16, 28, Sk_range32, 1 }, { "Sm", +1, Sm_range16, 53, Sm_range32, 11 }, - { "So", +1, So_range16, 114, So_range32, 59 }, + { "So", +1, So_range16, 112, So_range32, 62 }, + { "Sogdian", +1, 0, 0, Sogdian_range32, 1 }, { "Sora_Sompeng", +1, 0, 0, Sora_Sompeng_range32, 2 }, - { "Soyombo", +1, 0, 0, Soyombo_range32, 3 }, + { "Soyombo", +1, 0, 0, Soyombo_range32, 2 }, { "Sundanese", +1, Sundanese_range16, 2, 0, 0 }, { "Syloti_Nagri", +1, Syloti_Nagri_range16, 1, 0, 0 }, { "Syriac", +1, Syriac_range16, 4, 0, 0 }, @@ -5895,7 +6035,7 @@ { "Takri", +1, 0, 0, Takri_range32, 2 }, { "Tamil", +1, Tamil_range16, 16, 0, 0 }, { "Tangut", +1, 0, 0, Tangut_range32, 3 }, - { "Telugu", +1, Telugu_range16, 13, 0, 0 }, + { "Telugu", +1, Telugu_range16, 12, 0, 0 }, { "Thaana", +1, Thaana_range16, 1, 0, 0 }, { "Thai", +1, Thai_range16, 2, 0, 0 }, { "Tibetan", +1, Tibetan_range16, 7, 0, 0 }, @@ -5911,7 +6051,7 @@ { "Zp", +1, Zp_range16, 1, 0, 0 }, { "Zs", +1, Zs_range16, 7, 0, 0 }, }; -const int num_unicode_groups = 177; +const int num_unicode_groups = 184; } // namespace re2